TASLP 2008 - PDF Preprint Papers

TASLP 2008

Teaser Browsing | Click Here

Title Browsing | Click Here

Wall of Fame | Most Viewed TASLP-2008 Paper

click to vote

TASLP
2008

229views more TASLP 2008»

System Combination for Machine Translation of Spoken and Written Language

13 years 4 months ago

Download www-i6.informatik.rwth-aachen.de

This paper describes an approach for computing a consensus translation from the outputs of multiple machine translation (MT) systems. The consensus translation is computed by weigh...

Evgeny Matusov, Gregor Leusch, Rafael E. Banchs, N...

claim paper

Read More »

Disclaimer and Copyright Notice

Sciweavers respects the rights of all copyright holders and in this regard, authors are only allowed to share a link to their preprint paper on their own website. Every contribution is associated with a desciptive image. It is the sole responsibility of the authors to ensure that their posted image is not copyright infringing. This service is compliant with IEEE copyright.

Id	Views	Title	Status

1	229	System Combination for Machine Translation of Spoken and Written Language	claim
2	207	Joint Morphological-Lexical Language Modeling for Processing Morphologically Rich Languages With Application to Dialectal Arabic	claim
3	201	Syntactically Lexicalized Phrase-Based SMT	claim
4	176	Analysis of Minimum Distances in High-Dimensional Musical Spaces	claim
5	175	A Variable Step-Size Affine Projection Algorithm Designed for Acoustic Echo Cancellation	claim
6	158	Score-Independent Audio Features for Description of Music Expression	claim
7	154	Capturing Local Variability for Speaker Normalization in Speech Recognition	claim
8	150	Automatic Prosodic Event Detection Using Acoustic, Lexical, and Syntactic Evidence	claim
9	149	Music Retrieval Over Wireless Ad-Hoc Networks	claim
10	149	Using Articulatory Representations to Detect Segmental Errors in Nonnative Pronunciation	claim
11	148	A Minimum Distortion Noise Reduction Algorithm With Multiple Microphones	claim
12	148	Combining Spectral Representations for Large-Vocabulary Continuous Speech Recognition	claim
13	143	Strategies to Improve the Robustness of Agglomerative Hierarchical Clustering Under Data Source Variation for Speaker Diarization	claim
14	142	HMM Word and Phrase Alignment for Statistical Machine Translation	claim
15	141	Unsupervised Pattern Discovery in Speech	claim
16	140	Acoustic Chord Transcription and Key Extraction From Audio Using Key-Dependent HMMs Trained on Synthesized Audio	claim
17	136	Distortion Estimation in Compressed Music Using Only Audio Fingerprints	claim
18	136	On Acoustic Diversification Front-End for Spoken Language Identification	claim
19	134	Semantic Role Labeling Using a Grammar-Driven Convolution Tree Kernel	claim
20	133	Evaluation of Objective Quality Measures for Speech Enhancement	claim
21	133	Adaptive System Identification in the Short-Time Fourier Transform Domain Using Cross-Multiplicative Transfer Function Approximation	claim
22	133	Minimum Mean-Squared Error Estimation of Mel-Frequency Cepstral Coefficients Using a Novel Distortion Model	claim
23	131	Histogram-Based Quantization for Robust and/or Distributed Speech Recognition	claim
24	131	A Noise-Robust FFT-Based Auditory Spectrum With Application in Audio Classification	claim
25	129	Chroma Binary Similarity and Local Alignment Applied to Cover Song Identification	claim
26	126	LyricAlly: Automatic Synchronization of Textual Lyrics to Acoustic Music Signals	claim
27	124	Sparse Linear Regression With Structured Priors and Application to Denoising of Musical Audio	claim
28	124	Joint Dereverberation and Residual Echo Suppression of Speech Signals in Noisy Environments	claim
29	124	Semantic Annotation and Retrieval of Music and Sound Effects	claim
30	123	Normalized Cuts for Predominant Melodic Source Separation	claim
31	122	Challenging Uncertainty in Query by Humming Systems: A Fingerprinting Approach	claim
32	120	Rapid Speaker Adaptation Using Clustered Maximum-Likelihood Linear Basis With Sparse Training Data	claim
33	117	Auditory-Based Spectral Amplitude Estimators for Speech Enhancement	claim
34	115	Recognition of Dialogue Acts in Multiparty Meetings Using a Switching DBN	claim
35	112	A Study in Efficiency and Modality Usage in Multimodal Form Filling Systems	claim
36	110	A Backward-Compatible Multichannel Audio Codec	claim
37	108	An Online Relevant Set Algorithm for Statistical Machine Translation	claim
38	108	A Regression Approach to Music Emotion Recognition	claim
39	106	Multipitch Analysis of Polyphonic Music and Speech Signals Using an Auditory Model	claim
40	105	Optimizing the Performance of Spoken Language Recognition With Discriminative Training	claim
41	104	Tracking of Nonstationary Noise Based on Data-Driven Recursive Noise Power Estimation	claim
42	104	A New Model-Based Algorithm for Optimizing the MPEG-AAC in MS-Stereo	claim
43	102	On the Importance of the Pearson Correlation Coefficient in Noise Reduction	claim
44	102	Acoustic Source Separation of Convolutive Mixtures Based on Intensity Vector Statistics	claim
45	102	Computational Models of Similarity for Drum Samples	claim
46	101	Speaker Identification Using Instantaneous Frequencies	claim
47	100	Noise Tracking Using DFT Domain Subspace Decompositions	claim
48	99	Epoch Extraction From Speech Signals	claim
49	98	Unsupervised Single-Channel Music Source Separation by Average Harmonic Structure Modeling	claim
50	98	An Integrative and Discriminative Technique for Spoken Utterance Classification	claim
51	96	Fast Tracing of Acoustic Beams and Paths Through Visibility Lookup	claim
52	96	Binaural Tracking of Multiple Moving Sources	claim
53	93	Phantom Materialization: A Novel Method to Enhance Stereo Audio Reproduction on Headphones	claim
54	92	Hybrid Signal-and-Link-Parametric Speech Quality Measurement for VoIP Communications	claim
55	91	Time-Scale Modification of Audio Signals Using Enhanced WSOLA With Management of Transients	claim
56	90	Efficient Realization of Wave Digital Components for Physical Modeling and Sound Synthesis	claim
57	89	A Cascaded Broadcast News Highlighter	claim
58	88	Transforming Perceived Vocal Effort and Breathiness Using Adaptive Pre-Emphasis Linear Prediction	claim
59	84	Searching Musical Audio Using Symbolic Queries	claim
60	82	Union of MDCT Bases for Audio Coding	claim
61	81	Instrument-Specific Harmonic Atoms for Mid-Level Music Representation	claim
62	81	Regularized Linear Prediction of Speech	claim
63	78	Factor Analyzed Subspace Modeling and Selection	claim
64	75	Efficient Index-Based Audio Matching	claim
65	72	Normalization of the Speech Modulation Spectra for Robust Speech Recognition	claim
66	71	Dual-Source Transfer-Function Generalized Sidelobe Canceller	claim
67	70	Linearly Constrained Minimum Variance Source Localization and Spectral Estimation	claim
68	64	Improved A Posteriori Speech Presence Probability Estimation Based on a Likelihood Ratio With Fixed Priors	claim
69	61	Spectral Representations of Nonmodal Phonation	claim
70	58	Robust Speech Recognition Using a Cepstral Minimum-Mean-Square-Error-Motivated Noise Suppressor	claim

Sciweavers

Explore & Download

Productivity Tools

Document Tools

Image Tools

Sciweavers